{"list":"other","total":151,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"1604.00449","title":"3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction","created":"2016-04-02","cited_by_count":588},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2111.11426","title":"Neural Fields in Visual Computing and Beyond","created":"2021-11-22","cited_by_count":540},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455},{"id":"2012.03918","title":"NeRD: Neural Reflectance Decomposition from Image Collections","created":"2020-12-07","cited_by_count":449},{"id":"2011.03277","title":"Modular Primitives for High-Performance Differentiable Rendering","created":"2020-11-06","cited_by_count":441},{"id":"1711.07566","title":"Neural 3D Mesh Renderer","created":"2017-11-20","cited_by_count":437},{"id":"1904.01786","title":"Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning","created":"2019-04-03","cited_by_count":420},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"2501.12202","title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","created":"2025-01-21","cited_by_count":356},{"id":"1812.06216","title":"ABC: A Big CAD Model Dataset For Geometric Deep Learning","created":"2018-12-15","cited_by_count":341},{"id":"2112.03221","title":"Text2Mesh: Text-Driven Neural Stylization for Meshes","created":"2021-12-06","cited_by_count":334},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"2302.01721","title":"TEXTure: Text-Guided Texturing of 3D Shapes","created":"2023-02-03","cited_by_count":304},{"id":"2203.13333","title":"CLIP-Mesh: Generating textured meshes from text using pretrained image-text models","created":"2022-03-24","cited_by_count":281},{"id":"1711.10337","title":"Are GANs Created Equal? A Large-Scale Study","created":"2017-11-28","cited_by_count":267},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260},{"id":"2303.11396","title":"Text2Tex: Text-driven Texture Synthesis via Diffusion Models","created":"2023-03-20","cited_by_count":235},{"id":"1908.01210","title":"Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer","created":"2019-08-03","cited_by_count":221},{"id":"1905.07259","title":"Texture Fields: Learning Texture Representations in Function Space","created":"2019-05-17","cited_by_count":210},{"id":"1605.04797","title":"Thingi10K: A Dataset of 10,000 3D-Printing Models","created":"2016-05-16","cited_by_count":183},{"id":"2506.15442","title":"Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material","created":"2025-06-18","cited_by_count":165},{"id":"1506.08959","title":"A Large-Scale Car Dataset for Fine-Grained Categorization and Verification","created":"2015-06-30","cited_by_count":130},{"id":"2312.13913","title":"Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models","created":"2023-12-21","cited_by_count":123},{"id":"1810.09718","title":"Single-Image SVBRDF Capture with a Rendering-Aware Deep Network","created":"2018-10-23","cited_by_count":116},{"id":"1911.05063","title":"Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research","created":"2019-11-12","cited_by_count":98},{"id":"2505.07747","title":"Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets","created":"2025-05-12","cited_by_count":87},{"id":"2311.12891","title":"Text-Guided Texturing by Synchronized Multi-View Diffusion","created":"2023-11-21","cited_by_count":86},{"id":"2312.11360","title":"Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering","created":"2023-12-18","cited_by_count":84},{"id":"1809.01995","title":"Dense Pose Transfer","created":"2018-09-06","cited_by_count":83},{"id":"2210.11277","title":"TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition","created":"2022-10-20","cited_by_count":83},{"id":"2312.06704","title":"SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction","created":"2023-12-10","cited_by_count":77},{"id":"1908.07117","title":"360-Degree Textures of People in Clothing from a Single Image","created":"2019-08-20","cited_by_count":75},{"id":"2311.15855","title":"SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion","created":"2023-11-27","cited_by_count":72},{"id":"2004.04180","title":"Leveraging 2D Data to Learn Textured 3D Mesh Generation","created":"2020-04-08","cited_by_count":69},{"id":"2204.02411","title":"Texturify: Generating Textures on 3D Shape Surfaces","created":"2022-04-05","cited_by_count":65},{"id":"2308.10490","title":"Texture Generation on 3D Meshes with Point-UV Diffusion","created":"2023-08-21","cited_by_count":63},{"id":"1712.04695","title":"UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition","created":"2017-12-13","cited_by_count":62},{"id":"2305.06131","title":"Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era","created":"2023-05-10","cited_by_count":61},{"id":"2003.02050","title":"Learning to Transfer Texture from Clothing Images to 3D Humans","created":"2020-03-04","cited_by_count":58},{"id":"2108.12958","title":"3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations","created":"2021-08-30","cited_by_count":58},{"id":"2112.01530","title":"StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions","created":"2021-12-02","cited_by_count":58},{"id":"2402.13251","title":"FlashTex: Fast Relightable Mesh Texturing with LightControlNet","created":"2024-02-20","cited_by_count":56},{"id":"1910.11322","title":"TexturePose: Supervising Human Mesh Estimation with Texture Consistency","created":"2019-10-24","cited_by_count":53},{"id":"2401.09416","title":"TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion","created":"2024-01-17","cited_by_count":52},{"id":"2407.02430","title":"Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects","created":"2024-07-02","cited_by_count":52},{"id":"2003.08932","title":"GIQA: Generated Image Quality Assessment","created":"2020-03-19","cited_by_count":51},{"id":"2405.17176","title":"DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models","created":"2024-05-27","cited_by_count":50},{"id":"2411.14740","title":"TEXGen: a Generative Diffusion Model for Mesh Textures","created":"2024-11-22","cited_by_count":46},{"id":"1812.00020","title":"TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes","created":"2018-11-30","cited_by_count":45},{"id":"2508.10868","title":"TexVerse: A Universe of 3D Objects with High-Resolution Textures","created":"2025-08-14","cited_by_count":45},{"id":"2311.17261","title":"SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors","created":"2023-11-28","cited_by_count":43},{"id":"2401.06056","title":"MatSynth: A Modern PBR Materials Dataset","created":"2024-01-11","cited_by_count":42},{"id":"2109.12922","title":"ClipMatrix: Text-controlled Creation of 3D Textured Meshes","created":"2021-09-27","cited_by_count":40},{"id":"2204.03105","title":"AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis","created":"2022-04-06","cited_by_count":39},{"id":"2303.15764","title":"X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance","created":"2023-03-28","cited_by_count":37}],"next_cursor":"100"}